The diagnostic performance of ultrasound computer-aided diagnosis system for distinguishing breast masses: a prospective multicenter study

被引：28

作者：

Wei, Qi ^{[1
]}

Yu-Jing Yan ^{[1
]}

Ge-Ge Wu ^{[1
]}

Xi-Rong Ye ^{[2
]}

Jiang, Fan ^{[3
]}

Liu, Jie ^{[4
]}

Wang, Gang ^{[5
]}

Wang, Yi ^{[6
]}

Song, Juan ^{[7
]}

Zhi-Ping Pan ^{[8
]}

Jin-Hua Hu ^{[9
]}

Chao-Ying Jin ^{[5
]}

Wang, Xiang ^{[6
]}

Dietrich, Christoph F. ^{[10
]}

Xin-Wu Cui ^{[1
]}

机构：

[1] Huazhong Univ Sci & Technol, Tongji Hosp, Tongji Med Coll, Dept Med Ultrasound, 1095 Jiefang Ave, Wuhan 430030, Hubei, Peoples R China

[2] Cent Hosp EDong Healthcare, Dept Med Ultrasound, Huangshi 435000, Hubei, Peoples R China

[3] Anhui Med Univ, Dept Med Ultrasound, Hosp 2, Hefei 230601, Anhui, Peoples R China

[4] Three Gorges Univ, Yichang Gen Hosp, Dept Med Ultrasound, Renmin Hosp, Yichang 443099, Hubei, Peoples R China

[5] Taizhou Hosp Zhejiang Prov, Dept Med Ultrasound, Linhai 318000, Zhejiang, Peoples R China

[6] Macheng Peoples Hosp, Dept Med Ultrasound, Macheng 438300, Hubei, Peoples R China

[7] Hubei Univ Med, Xiangyang 1 Peoples Hosp, Dept Med Ultrasound, Affiliated Hosp, Xiangyang 441000, Hubei, Peoples R China

[8] Yixing Tradit Chinese Med Hosp, Dept Med Ultrasound, Yixing 214200, Jiangsu, Peoples R China

[9] Anhui Med Univ, Dept Med Ultrasound, Anqing Peoples Hosp 1, Anqing 246052, Anhui, Peoples R China

[10] Hirslanden Clin, Dept Internal Med, Schanzlihalde 11, CH-3013 Bern, Switzerland

来源：

EUROPEAN RADIOLOGY | 2022年 / 32卷 / 06期

基金：

中国国家自然科学基金;

关键词：

Breast cancer; Ultrasound imaging; Computer-assisted diagnosis; Biopsy; Artificial intelligence; S-DETECT; ULTRASONOGRAPHY; AGREEMENT; WOMEN; US;

D O I：

10.1007/s00330-021-08452-1

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

Objectives To evaluate the diagnostic value of computer-aided diagnosis (CAD) software on ultrasound in distinguishing benign and malignant breast masses and avoiding unnecessary biopsy. Methods This prospective, multicenter study included patients who were scheduled for pathological diagnosis of breast masses between April 2019 and November 2020. Ultrasound images, videos, CAD analysis, and BI-RADS were obtained. The AUC, accuracy, sensitivity, specificity, PPV, and NPV were calculated and compared with radiologists. Results Overall, 901 breast masses in 901 patients were enrolled in this study. The accuracy, sensitivity, specificity, PPV and NPV of CAD software were 89.6%, 94.2%, 87.0%, 80.4%, and 96.3, respectively, in the long-axis section; 89.0%, 91.4%, 87.7%, 80.8%, and 94.7%, respectively, in the short-axis section. With BI-RADS 4a as the cut-off value, CAD software has a higher AUC (0.906 vs 0.734 vs 0.696, all p < 0.001) than both experienced and less experienced radiologists. With BI-RADS 4b as the cut-off value, CAD software showed better AUC than less experienced radiologists (0.906 vs 0.874, p < 0.001), but not superior to experienced radiologists (0.906 vs 0.883, p = 0.057). After the application of CAD software, the unnecessary biopsy rate of BI-RADS categories 4 and 5 was significantly decreased (33.0% vs 11.9%, 37.8% vs 14.5%), and the malignant rate of biopsy in category 4a was significantly increased (11.6% vs 40.7%, 7.4% vs 34.9%, all p < 0.001). Conclusions CAD software on ultrasound can be used as an effective auxiliary diagnostic tool for differential diagnosis of benign and malignant breast masses and reducing unnecessary biopsy.

引用

页码：4046 / 4055

页数：10

共 27 条

[1]

[Anonymous], 2014, WHO POSITION PAPER M

[2]

[Anonymous], 2013, ACR BI-RADS atlas, breast imaging reporting and data system

[3] Application of Computer-Aided Diagnosis on Breast Ultrasonography: Evaluation of Diagnostic Performances and Agreement of Radiologists According to Different Levels of Experience [J].